#7025 [localllm] Cannot connect to http://127.0.0.1:11434/v1. Check network access or verify local server deployment.Request t

2601**721 Posted at: 1 hour ago

[localllm] Cannot connect to http://127.0.0.1:11434/v1. Check network access or verify local server deployment.
Request timed out.
Traceback (most recent call last):
File "httpx\_transports\default.py", line 101, in map_httpcore_exceptions
File "httpx\_transports\default.py", line 250, in handle_request
File "httpcore\_sync\connection_pool.py", line 216, in handle_request
File "httpcore\_sync\connection_pool.py", line 196, in handle_request
File "httpcore\_sync\connection.py", line 101, in handle_request
File "httpcore\_sync\http11.py", line 143, in handle_request
File "httpcore\_sync\http11.py", line 113, in handle_request
File "httpcore\_sync\http11.py", line 186, in _receive_response_headers
File "httpcore\_sync\http11.py", line 224, in _receive_event
File "httpcore\_backends\sync.py", line 124, in read
File "contextlib.py", line 153, in exit
File "httpcore\_exceptions.py", line 14, in map_exceptions
httpcore.ReadTimeout: timed out

The a
......
\completions.py", line 1215, in create
File "openai\_base_client.py", line 1332, in post
File "openai\_base_client.py", line 1055, in request
openai.APITimeoutError: Request timed out.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 89, in run
File "videotrans\task\_stage_translate.py", line 31, in trans
File "videotrans\translator\_runner.py", line 67, in run
File "videotrans\translator\_base.py", line 71, in run
File "videotrans\translator\_base.py", line 209, in _run_srt
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 400, in
File "concurrent\futures\_base.py", line 451, in result
File "concurrent\futures\_base.py", line 403, in __get_result
File "tenacity\__init__.py", line 480, in call
File "videotrans\translator\_openaicompat.py", line 92, in _item_task
videotrans.configure.excepts.StopTask: [localllm] Cannot connect to http://127.0.0.1:11434/v1. Check network access or verify local server deployment.
Request timed out.

cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: H:/index-3 (1080p aac)/index-3 (1080p_aac).mp4,
输出结果保存到文件夹: L:/Dub Studio/index-3 (1080p_aac)-mp4,
临时文件夹: C:/AIDubbingSuite/Apps/pyVideoTrans/tmp/20660/9e9729ddd2
已选 清理已存在
已启用CUDA加速
未选 降噪
已选 识别说话人，最大说话人数量不限制
STT Service:faster-whisper(Built-in), large-v3, 发音语言: English, 断句方式:默认断句
TranslateSrt:CompatibleAI/LocalModel,原始语言:English,目标语言:Vietnamese, 已选 SendSRT
TTS Service:OmniVoice(Built-in), 角色:clone, 配音语言:Vietnamese, 未选 二次语音识别
音量:+5%, 语速:+0%, 已选 音频加速, 未选 视频慢速
字幕: No Subtitles
已选 分离人声与背景声, 已选 重新嵌入背景声, 背景音量0.8, 背景声音时长 短于 视频时长时: 拉长(降速播放),存在分离后的纯净人声文件,存在分离后的背景声音文件
已选 仅输出mp4

=
system:Windows-10-10.0.19045-SP0
version:v4.11
frozen:True
language:en
root_dir:C:/AIDubbingSuite/Apps/pyVideoTrans

1 Replies

#1 DeepSeek reply at 1 hour ago

This error means pyVideoTrans cannot reach your local LLM service at http://127.0.0.1:11434/v1 (typically Ollama). The ReadTimeout indicates the connection was established, but the server did not respond within the timeout period. This usually happens when the local service is not running, is still loading the model, or is overloaded by a large request.

Troubleshooting steps

  1. Verify the service is running

    • Open http://127.0.0.1:11434 in your browser. If nothing loads, Ollama is not running.
    • In a terminal, run ollama list to see if Ollama is active and which models are available.

  2. Confirm the model name matches

    • In pyVideoTrans, the configured model name must exactly match one of the models returned by ollama list.
    • If you haven't pulled a model yet, run ollama pull <model_name> (e.g. ollama pull qwen2.5:7b).

  3. Reduce the workload for local LLM

    • Go to Menu → Tools → Advanced Options → Subtitle Translation.
    • Set AI translation batch lines to 1.
    • Uncheck "Send complete subtitles" (发送完整字幕). Local models handle short texts much better and are far more likely to respond within the timeout.

  4. Give the model time to load

    • The first request after starting the server is often slow because the model must be loaded into memory. Send one test translation and wait; if it times out, retry after the model is warm.

  5. Check proxy settings

    • Clear the proxy field on the main interface if you entered something. Local services like 127.0.0.1 are automatically bypassed, but an invalid proxy address can still break the request.

  6. If all else fails

    • Switch to a cloud translation channel (e.g. DeepSeek) for now, or provide the latest log from logs/ (bottom ~30 lines) for further analysis.

Please consult the relevant documentation:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource